Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1451 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.4875. Min Act: -0.1700
Data Index: 3206245 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.3625. Min Act: -0.1700
Data Index: 7806375 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.2687. Min Act: -0.1700
Data Index: 2050237 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.1437. Min Act: -0.1700
Data Index: 3930272 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.1437. Min Act: -0.1700
Data Index: 3748588 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.1124. Min Act: -0.1700
Data Index: 6361263 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.1124. Min Act: -0.1700
Data Index: 7171365 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.1124. Min Act: -0.1700
Data Index: 2861557 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.0812. Min Act: -0.1700
Data Index: 6655155 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.0812. Min Act: -0.1700
Data Index: 7334632 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.0812. Min Act: -0.1700
Data Index: 2334072 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.0499. Min Act: -0.1700
Data Index: 4612027 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.0187. Min Act: -0.1700
Data Index: 8583244 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.0499. Min Act: -0.1700
Data Index: 3191314 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4875. Min Range: -4.4875
Max Act: 3.9874. Min Act: -0.1700
Data Index: 2049366 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4875. Min Range: -4.4875
Max Act: 4.0187. Min Act: -0.1700
Data Index: 5673631 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4875. Min Range: -4.4875
Max Act: 3.9874. Min Act: -0.1700
Data Index: 7432184 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4875. Min Range: -4.4875
Max Act: 3.9874. Min Act: -0.1700
Data Index: 1135799 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4875. Min Range: -4.4875
Max Act: 3.9874. Min Act: -0.1700
Data Index: 841452 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4875. Min Range: -4.4875
Max Act: 3.9874. Min Act: -0.1700
Data Index: 5261955 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19